Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "whatever the."

    oai_token-act-pair · gpt-3.5-turbo

    references to various outcomes or situations that may vary based on context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.75
    ridor
    -0.71
    ²
    -0.69
    arie
    -0.68
    MRI
    -0.67
    ciating
    -0.65
    eting
    -0.63
    ãĥ¼ãĥ³
    -0.62
    ANS
    -0.62
    és
    -0.61
    POSITIVE LOGITS
    faith
    0.71
     faults
    0.70
     merits
    0.67
     particulars
    0.62
     fate
    0.61
     outcome
    0.61
     denomination
    0.60
     adherent
    0.59
     disagreements
    0.59
     extent
    0.58
    Act Density 0.099%

    No Known Activations